Borrowing it
Nothing to install: this file belongs to akaghef/M3E. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/akaghef/M3E/main/.claude/skills/pr-review/SKILL.mdgit clone --depth 1 https://github.com/akaghef/M3EWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/akaghef/m3e/pr-review)<a href="https://agentmods.dev/skills/akaghef/m3e/pr-review"><img src="https://agentmods.dev/badge/skills/akaghef/m3e/pr-review/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/akaghef/m3e/pr-review"><img src="https://agentmods.dev/badge/skills/akaghef/m3e/pr-review.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00194 | $0.02009 |
| Opus 5.5 | $0.00078 | $0.00804 |
| Sonnet 5.5 | $0.00039 | $0.00402 |
| Haiku 4.5 | $0.00019 | $0.00201 |
Grade A, and why
pr-review scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 5d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 238 lines — stays where its author put it; the contents beside it link to each section on GitHub.
pr-review — PR レビュー・マージ・事後処理
PR作成後のマネージャー側フロー全体を扱う。
PR受領 → 差分レビュー → 検証 → 判定 → マージ → 事後処理
Step 1: PR の読み込み
PR番号 or URLが指定された場合:
gh pr view <number> --json title,body,headRefName,baseRefName,files,commits,state
gh pr diff <number>
PR番号が不明な場合:
# open なPR一覧(base=dev-beta)
gh pr list --base dev-beta --state open
読み取る情報:
- タイトル・概要
- ソースブランチ → ベースブランチ
- コミット一覧
- 変更ファイル一覧と差分
- 既存のレビューコメント
Step 2: レビュー
3つの観点で差分を評価する。devM3E の reviewer agent と同じ基準だが、PR文脈に特化。
2a. Spec整合チェック
変更が関連specに準拠しているか確認する。
- 変更ファイルから関連specを特定(
references/spec_index.md参照) - データモデル不変条件の維持
- Commandパターン(undo/redo)の維持
- scope/alias ルールへの適合
specを読む必要がある場合は docs/03_Spec/ から該当文書を読む。
2b. コード品質チェック
- 型安全性(不必要な
any、型アサーション) - エラーハンドリング(fail-closed か)
- パフォーマンス懸念(O(n²)ループ、不要な再レンダリング)
- テストカバレッジ(新規コードにテストがあるか)
2c. 運用ルール準拠
- コミットメッセージが imperative 形式か
- daily note(
docs/daily/YYMMDD.md)が更新されているか - Decision Pool に記録すべき設計判断が埋もれていないか
- ブランチ名がロールに合致しているか(visual→dev-visual 等)
Step 3: 検証(オプション)
差分の性質に応じて検証を実行する。
| 変更の性質 | 実行する検証 |
|---|---|
| TypeScript コード | npx tsc --noEmit |
| テスト関連 | npx vitest run |
| ビルド影響あり | npm run build |
| UI変更 | Playwright(該当テストがあれば) |
| ドキュメントのみ | スキップ |
検証を実行する場合は、PR のブランチをチェックアウトして行う:
gh pr checkout <number>
cd beta
npx tsc --noEmit && npx vitest run && npm run build
Step 4: 判定
レビュー結果を以下の形式でユーザーに報告する。
## PR #{number}: {title}
### 判定: ✅ approve / ⚠️ comment / ❌ request-changes
### 変更サマリー
{ファイル数}ファイル, +{追加行} -{削除行}
影響範囲: {beta/ | docs/ | scripts/ 等}
### レビュー結果
- [pass|fail] Spec整合: {detail}
- [pass|fail] コード品質: {detail}
- [pass|fail] 運用ルール: {detail}
### 検証結果
- tsc: pass/fail
- test: pass/fail ({n}/{total})
- build: pass/fail
### issue(あれば)
- [{severity}] {description}
### 推奨アクション
{マージしてよい / 修正が必要 / 要議論}
判定基準
| 判定 | 条件 |
|---|---|
| approve | issue なし or nit のみ。検証パス |
| comment | minor issue あるがマージをブロックしない |
| request-changes | major/critical issue あり。修正が必要 |
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 5d ago First seen · 238 lines · 194 tokens per session scan A e322be2ad244
pr-review is a skill published in the GitHub repository akaghef/M3E (11 stars, last pushed 5d ago), licensed MIT. It adds 194 tokens to every session and 2,009 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-02.
Other skills, from other repositories
review-implement-phase
Implements triaged review actions, commits focused fixes, and posts Done plus resolves threads. Use when the user wants only the implementation phase of the review-framework workflow.
pr
Draft a PR body from OMC's paper trail — the smallest visual that proves the change, evidence consumed from the verify protocol (never re-collected), reversibility from the ADR test on the diff, glossary language throughout.
engram-branch-pr
PR creation workflow for Engram following the issue-first enforcement system. Trigger: When creating a pull request, opening a PR, or preparing changes for review.
verify-behavior
Verify or reproduce visible product behavior by driving the real UI with pi-computer-use's checked tools, requiring verified expect postconditions and durable state evidence for meaningful UI flows. Use when triage needs visual reproduction, implementation needs behavioral proof, review needs interactive confirmation…
github-contributor
A step-by-step guide for contributing code, tests, documentation, or build changes to open-source projects you do not maintain. It explains how to prepare a pull request that follows the project’s rules and is easier for maintainers to review.
revdiff
Review diffs, files, and documents with inline annotations in a TUI overlay, or answer questions about revdiff usage, configuration, themes, and keybindings. Opens revdiff in agterm/tmux/zellij/herdr/kitty/wezterm/cmux/ghostty/iterm2/emacs-vterm, captures annotations, and addresses them. Works in git, hg, and jj repos…